Search Results for author:
Found 25 papers, 15 papers with code
Alzheimer's disease detection in PSG signals
This study delves into the potential of utilizing sleep-related electroencephalography (EEG) signals acquired through polysomnography (PSG) for the early detection of AD.
Training Implicit Generative Models via an Invariant Statistical Loss
In this work, we develop a discriminator-free method for training one-dimensional (1D) generative implicit models and subsequently expand this method to accommodate multivariate cases.
Efficient local linearity regularization to overcome catastrophic overfitting
Our regularization term can be theoretically linked to curvature of the loss function and is computationally cheaper than previous methods by avoiding Double Backpropagation.
Interpretable Spectral Variational AutoEncoder (ISVAE) for time series clustering
The best encoding is the one that is interpretable in nature.
Variational Mixture of HyperGenerators for Learning Distributions Over Functions
Recent approaches build on implicit neural representations (INRs) to propose generative models over function spaces.
Sleep Activity Recognition and Characterization from Multi-Source Passively Sensed Data
Sleep constitutes a key indicator of human health, performance, and quality of life.
Detecting train driveshaft damages using accelerometer signals and Differential Convolutional Neural Networks
Railway axle maintenance is critical to avoid catastrophic failures.
Heterogeneous Hidden Markov Models for Sleep Activity Recognition from Multi-Source Passively Sensed Data
Psychiatric patients' passive activity monitoring is crucial to detect behavioural shifts in real-time, comprising a tool that helps clinicians supervise patients' evolution over time and enhance the associated treatments' outcomes.
Multimodal hierarchical Variational AutoEncoders with Factor Analysis latent space
For this purpose, recent studies based on deep generative models merge all views into a nonlinear complex latent space, which can share information among views.
Multi-task longitudinal forecasting with missing values on Alzheimer's Disease
Machine learning techniques typically applied to dementia forecasting lack in their capabilities to jointly learn several tasks, handle time dependent heterogeneous data and missing values.
PyHHMM: A Python Library for Heterogeneous Hidden Markov Models
We introduce PyHHMM, an object-oriented open-source Python implementation of Heterogeneous-Hidden Markov Models (HHMMs).
Deep Autoregressive Models with Spectral Attention
In this paper, we propose a forecasting architecture that combines deep autoregressive models with a Spectral Attention (SA) module, which merges global and local frequency domain information in the model's embedded space.
Medical data wrangling with sequential variational autoencoders
Medical data sets are usually corrupted by noise and missing data.
Unsupervised Learning of Global Factors in Deep Generative Models
We present a novel deep generative model based on non i. i. d.
Boosting offline handwritten text recognition in historical documents with few labeled lines
In this paper, we face the problem of offline handwritten text recognition (HTR) in historical documents when few labeled samples are available and some of them contain errors in the train set.
Bayesian Sparse Factor Analysis with Kernelized Observations
In particular, we combine probabilistic factor analysis with what we refer to as kernelized observations, in which the model focuses on reconstructing not the data itself, but its relationship with other data points measured by a kernel function.
Sparse Semi-supervised Heterogeneous Interbattery Bayesian Analysis
The Bayesian approach to feature extraction, known as factor analysis (FA), has been widely studied in machine learning to obtain a latent representation of the data.
Deep Sequential Models for Suicidal Ideation from Multiple Source Data
This article presents a novel method for predicting suicidal ideation from Electronic Health Records (EHR) and Ecological Momentary Assessment (EMA) data using deep sequential models.
Improved BiGAN training with marginal likelihood equalization
We propose a novel training procedure for improving the performance of generative adversarial networks (GANs), especially to bidirectional GANs.
Probabilistic Time of Arrival Localization
In this paper, we take a new approach for time of arrival geo-localization.
Handling Incomplete Heterogeneous Data using VAEs
Variational autoencoders (VAEs), as well as other generative models, have been shown to be efficient and accurate for capturing the latent structure of vast amounts of complex high-dimensional data.
Boosting Handwriting Text Recognition in Small Databases with Transfer Learning
We first investigate, for a reduced and fixed number of training samples, 350 lines, how the learning from a large database, the IAM, can be transferred to the learning of the CLC of a reduced database, Washington.
WHAT ARE GANS USEFUL FOR?
In this paper, we noticed that even though GANs might not be able to generate samples from the underlying distribution (or we cannot tell at least), they are capturing some structure of the data in that high dimensional space.
An Application of Tree-Structured Expectation Propagation for Channel Decoding
We show an application of a tree structure for approximate inference in graphical models using the expectation propagation algorithm.
